Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1068 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0282. Min Act: -0.0004

Data Index: 838017 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0283. Min Act: -0.0003

Data Index: 20892 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1223533 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0268. Min Act: -0.0003

Data Index: 614007 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1331761 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0251. Min Act: -0.0004

Data Index: 1332100 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1103768 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1223802 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0258. Min Act: -0.0003

Data Index: 945740 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0249. Min Act: -0.0003

Data Index: 833469 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0250. Min Act: -0.0003

Data Index: 309563 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0254. Min Act: -0.0004

Data Index: 717796 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0246. Min Act: -0.0003

Data Index: 323203 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1325106 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0241. Min Act: -0.0003

Data Index: 526561 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0253. Min Act: -0.0003

Data Index: 453802 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0243. Min Act: -0.0002

Data Index: 556373 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1320217 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0235. Min Act: -0.0003

Data Index: 915623 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.0283. Min Range: -0.0283

Max Act: 0.0237. Min Act: -0.0004

Data Index: 822327 (C4 (Web Text))

Max Activating Token Index: 744